أبحاث أعضاء الهيئة الأكاديمية 2007

  • # -----> #

1. Ehab M. Mortaja
Speaker Independent Quranic Recognizer Based on Maximum Likelihood Linear Regression, Proceedings Of World Academy Of Science, Engineering And Technology Volume 20, 2007
Abstract—An automatic speech recognition system for the
formal Arabic language is needed. The Quran is the most formal
spoken book in Arabic, it is spoken all over the world. In this
research, an automatic speech recognizer for Quranic based speakerindependent
was developed and tested. The system was developed
based on the tri-phone Hidden Markov Model and Maximum
Likelihood Linear Regression (MLLR). The MLLR computes a set
of transformations which reduces the mismatch between an initial
model set and the adaptation data. It uses the regression class tree, as
well as, estimates a set of linear transformations for the mean and
variance parameters of a Gaussian mixture HMM system. The 30th
Chapter of the Quran, with five of the most famous readers of the
Quran, was used for the training and testing of the data. The chapter
includes about 2000 distinct words. The advantages of using the
Quranic verses as the database in this developed recognizer are the
uniqueness of the words and the high level of orderliness between
verses. The level of accuracy from the tested data ranged 68 to 85%.
Abstract An automatic speech recognition system for theformal Arabic language is needed. The Quran is the most formalspoken book in Arabic, it is spoken all over the world. In thisresearch, an automatic speech recognizer for Quranic based speakerindependentwas developed and tested. The system was developedbased on the tri-phone Hidden Markov Model and MaximumLikelihood Linear Regression (MLLR). The MLLR computes a setof transformations which reduces the mismatch between an initialmodel set and the adaptation data. It uses the regression class tree, aswell as, estimates a set of linear transformations for the mean andvariance parameters of a Gaussian mixture HMM system. The 30thChapter of the Quran, with five of the most famous readers of theQuran, was used for the training and testing of the data. The chapterincludes about 2000 distinct words. The advantages of using theQuranic verses as the database in this developed recognizer are theuniqueness of the words and the high level of orderliness betweenverses. The level of accuracy from the tested data ranged 68 to 85%.

2. Tawfiq S. Barhoom
XML Context's Security Patterns Language: Description and Syntax, Information Technology Journal - 30-ITJ-DOI, 2007


3. Nabil M. Hewahi
Intelligent Tutoring System: Hierarchical Rule (HR) as a knowledge representation and adaptive Pedagogical Model, Information Technology Journal, 2007


4. Nabil M. Hewahi, Mohammed Hannoush, Shady Mohanan
Document Imaging Systems, Ubiquitous Computing and Communication, 2007


5. Nabil M. Hewahi and Motaz.K. Saad
Class Outlier Mining: Distance-Based Approach, International Journal of Intelligent Technology, 2007


6. Nabil M. Hewahi
Vehicle Warning System: Driver 's Reaction Factor, Arab Conference of Information Technology ACIT' 2007


7. Ala'a M. Al-Halees
Arabic Text Classification Using Maximum Entropy In The Islamic University Journal (Series of Natural Studies and Engineering) .Vol 15, No. 1 Jan. pp. 157-167, 2007


8. Ashraf M. Alattar
A New Stereo Correspondence Method for Snake-Based Object Segmentation
ICIP 2007
10. Tawfiq S. Barhoom
THE ROLE OF AGENTS IN SEARCHING LOCAL NETWORK, The International Engineering Conference on Construction and Development – IUG – Gaza- Palestine 2007